INDEX

Explanations

patterns related to numerical data or IP addresses

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SharedDtor

-0.99

 Normdatei

-0.97

StructEnd

-0.95

 الحره

-0.94

Autoritní

-0.93

RegistryLite

-0.93

 AssemblyTitle

-0.92

 gainera

-0.92

NUMX

-0.91

MLLoader

-0.90

POSITIVE LOGITS

0.52

0.47

0.46

0.45

0.43

prnewswire

0.42

0.41

جویان

0.41

Activations Density 0.559%

patterns related to numerical data or IP addresses

No Comments

No Known Activations